fix(staging): tolerate sandbox-infra-only FAILs (C9a/C9b) in deploy-staging verdict
Some checks failed
CI / test (push) Failing after 39s
CI / test (pull_request) Failing after 35s

The self-hosting orchestrator looped on deploy-staging -> development because
scripts/staging_check.py exited 1 on ANY failed check, so two infra-only checks
(C9a sandbox branch / C9b analyst-job — caused by SANDBOX bot accounts not being
members of the sandbox Plane project, NOT a pipeline regress) forced
staging_status: FAILED -> rollback -> loop, burning developer retries and tokens.

Direction (б) per ADR-001: classify staging checks as REAL (all pipeline checks,
fail-closed) vs SANDBOX_INFRA (narrow allowlist {C9a, C9b}, waivable). New leaf
module src/staging_verdict.py (stdlib-only, never-raise): classify_check +
compute_staging_verdict fold per-check results into a tolerant-but-fail-closed
verdict — any REAL failure -> FAILED/exit1 (safety net holds under any flag);
only C9a/C9b failed & tolerant -> SUCCESS/exit0 with waived list; only infra &
strict -> FAILED/exit1; any internal error -> FAILED/exit1 (never a false green).

staging_check.py now auto-classifies each check (public 3-tuple _items shape kept
as an ORCH-048 b6 regression guard), exposes categorized_items(), prints
INFRA-WAIVED/VERDICT lines, and exits via the verdict; new --strict flag forces
legacy strictness per-run. Kill-switch ORCH_STAGING_INFRA_TOLERANCE_ENABLED
(default true) restores legacy strict mode globally. launcher gains
action_stage_no_changes_note so "no changes to commit" on action stages is logged
as expected, not treated as under-delivery.

Contracts unchanged: STAGE_TRANSITIONS, QG_CHECKS registry, staging_status:/
deploy_status: frontmatter, hook exit-code (0/1/2), check_staging_status; no DB
migration. Docs: README, STAGING_CHECK.md, deployer.md, .env.example, CHANGELOG.

Refs: ORCH-061

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
2026-06-07 12:39:00 +00:00
parent 1d1208c136
commit 9070489968
15 changed files with 831 additions and 7 deletions

View File

@@ -51,6 +51,46 @@ import datetime
import urllib.request
import urllib.error
import urllib.parse
from collections import namedtuple
# ---------------------------------------------------------------------------
# ORCH-061: pure staging-verdict logic (classification + infra-tolerant verdict).
# Imported from src.staging_verdict — a stdlib-only leaf, safe to import inside
# the orchestrator-staging container (PYTHONPATH=/app, pattern B6 / ORCH-048).
# Guarded so the suite still runs (in strict mode) if src is somehow unimportable
# from a host invocation; the fallback NEVER yields a silent green (fail-closed).
# ---------------------------------------------------------------------------
try:
from src.staging_verdict import ( # type: ignore
classify_check as _classify_check,
compute_staging_verdict as _compute_staging_verdict,
REAL as _REAL,
SANDBOX_INFRA as _SANDBOX_INFRA,
)
except Exception: # pragma: no cover - exercised only on a broken host import
_classify_check = None
_compute_staging_verdict = None
_REAL = "real"
_SANDBOX_INFRA = "sandbox_infra"
_FallbackVerdict = namedtuple("StagingVerdict", "status exit_code waived summary")
def _classify(label: str) -> str:
"""Classify a check label via staging_verdict; fail-closed to REAL if absent."""
if _classify_check is not None:
return _classify_check(label)
return _REAL
def _verdict(items, infra_tolerant: bool):
"""Compute the suite verdict via staging_verdict; strict fail-closed fallback."""
if _compute_staging_verdict is not None:
return _compute_staging_verdict(items, infra_tolerant)
failed = [lbl for (lbl, ok, _cat) in items if not ok]
if failed:
return _FallbackVerdict("FAILED", 1, [], f"FAILED (strict fallback): {failed}")
return _FallbackVerdict("SUCCESS", 0, [], "SUCCESS (strict fallback): all green")
# ---------------------------------------------------------------------------
# Colour helpers
@@ -152,23 +192,47 @@ def _sign_payload(secret: str, body: bytes) -> str:
class Results:
def __init__(self):
# _items keeps the (label, passed, detail) 3-tuple shape that existing
# ORCH-048 B6 tests unpack — categories live in a PARALLEL list so the
# public tuple contract is unchanged.
self._items: list[tuple[str, bool, str]] = [] # (label, passed, detail)
self._categories: list[str] = [] # ORCH-061: REAL | SANDBOX_INFRA
def add(self, label: str, passed: bool, detail: str = ""):
def add(self, label: str, passed: bool, detail: str = "", category: str | None = None):
# ORCH-061: every check carries a category. None -> auto-classify by label
# (C9a/C9b -> SANDBOX_INFRA, everything else -> REAL). Fail-closed: an
# unknown label is REAL, so it still counts toward the safety net.
if category is None:
category = _classify(label)
self._items.append((label, passed, detail))
self._categories.append(category)
line = _ok(label) if passed else _fail(label)
if detail:
line += f" [{detail}]"
print(line)
def categorized_items(self) -> list[tuple[str, bool, str]]:
"""Rows as ``(label, passed, category)`` for ``compute_staging_verdict``."""
return [
(label, passed, cat)
for (label, passed, _detail), cat in zip(self._items, self._categories)
]
def summary(self) -> bool:
passed = sum(1 for _, ok, _ in self._items if ok)
total = len(self._items)
all_ok = passed == total
colour = _GREEN if all_ok else _RED
# ORCH-061: per-category breakdown so an operator can tell a REAL failure
# (regression — fail-closed) from a SANDBOX_INFRA one (waivable).
rows = self.categorized_items()
real_fail = [lbl for lbl, ok, cat in rows if not ok and cat == _REAL]
infra_fail = [lbl for lbl, ok, cat in rows if not ok and cat == _SANDBOX_INFRA]
print()
print(f"{_BOLD}{'='*60}{_RESET}")
print(f"{colour}{_BOLD} RESULT: {passed}/{total} checks PASS{_RESET}")
print(f" REAL failed : {real_fail or 'none'}")
print(f" SANDBOX_INFRA failed: {infra_fail or 'none'}")
print(f"{_BOLD}{'='*60}{_RESET}")
return all_ok
@@ -637,6 +701,28 @@ def _cleanup(plane_base, workspace, gitea_base, plane_headers, gitea_headers,
# Main
# ---------------------------------------------------------------------------
def _resolve_tolerance(cli_strict: bool) -> bool:
"""Resolve whether the infra-FAIL waiver is active (ORCH-061).
Precedence: an explicit ``--strict`` CLI flag forces it OFF (for honest manual
runs). Otherwise read ``settings.staging_infra_tolerance_enabled`` from the
running instance's own config (same pattern as B6's src.* import inside the
container). On ANY import/read error -> STRICT (False): we never waive when the
config is unreadable (fail-safe), and we say so.
"""
if cli_strict:
print(_info("tolerance: DISABLED via --strict (honest run)"))
return False
try:
from src.config import settings # noqa: WPS433 - lazy, mirrors B6
enabled = bool(settings.staging_infra_tolerance_enabled)
print(_info(f"tolerance: staging_infra_tolerance_enabled={enabled}"))
return enabled
except Exception as e:
print(_info(f"tolerance: config unavailable, defaulting to STRICT: {e}"))
return False
def main():
parser = argparse.ArgumentParser(
description="Live staging-stand check suite (ORCH-33)"
@@ -656,6 +742,15 @@ def main():
"full-real: also wait for the analyst agent (slow, costs credits)."
),
)
parser.add_argument(
"--strict",
action="store_true",
help=(
"ORCH-061: force strict suite — disable the sandbox-infra (C9a/C9b) "
"FAIL waiver even if staging_infra_tolerance_enabled=True. Use for an "
"honest 10/10 run once the sandbox bot accounts are provisioned."
),
)
args = parser.parse_args()
base = args.base_url.rstrip("/")
@@ -673,8 +768,23 @@ def main():
block_b(results)
block_c(base, results, args.mode)
all_ok = results.summary()
sys.exit(0 if all_ok else 1)
results.summary()
# ORCH-061: the EXIT CODE (which drives the deployer's staging_status verdict)
# comes from the infra-tolerant verdict, NOT a raw passed==total count. A run
# whose only failures are known sandbox-infra checks (C9a/C9b) is waived to
# exit 0 when tolerance is on; ANY real check failure still exits 1 (FR-4).
infra_tolerant = _resolve_tolerance(args.strict)
verdict = _verdict(results.categorized_items(), infra_tolerant)
if verdict.waived:
# FR-7 observability: make "green with an allowance" distinguishable from
# an honest green in the logs / captured deployer output.
print(f"{_YELLOW}{_BOLD}INFRA-WAIVED:{_RESET} "
f"{', '.join(verdict.waived)} "
f"(known sandbox-infra; real checks green)")
print(f"{_BOLD}VERDICT:{_RESET} {verdict.status} "
f"(exit {verdict.exit_code}) — {verdict.summary}")
sys.exit(verdict.exit_code)
if __name__ == "__main__":